Create_samples ending with Segmentation Fault
Hi!
I'm following this tutorial https://pythonprogramming.net/haar-ca... with the goal to build a crocodilo detector. When it comes to create the sample with:
opencv_createsamples -img 1.jpg -bg bg.txt -info info/info.lst -pngoutput info -maxxangle 0.5 -maxyangle 0.5 -maxzangle 0.5 -num 1950
I'm having the famous segmentation fault:
Create test samples from single image applying distortions...
Segmentation fault (core dumped)
This is my full output in the terminal:
Info file name: info/info.lst
Img file name: 1.jpg
Vec file name: (NULL)
BG file name: bg.txt
Num: 1950
BG color: 0
BG threshold: 80
Invert: FALSE
Max intensity deviation: 40
Max x angle: 0.5
Max y angle: 0.5
Max z angle: 0.5
Show samples: FALSE
Width: 24
Height: 24
Max Scale: -1
Create test samples from single image applying distortions...
Segmentation fault (core dumped)
I already tried to update my create_sample folder with https://github.com/opencv/opencv/tree... but still having the segmentation fault.
My workspace:
opencv_workspace
|_ info(folder)
|_data(folder)
|_ neg(folder)
|_ images.jpg
|_opencv(folder)
|_1.jpg
|_bg.txt
Hope I could make it clear! Thanks :D
yea, there is this bug, but you can't successfully train cascades with a single image anyway.
get a TON of real positive images, and try again.
and take that silly tutorial with a grain of salt -- in the end he can't detect his watch.
also, artificial distortions, a no-go for anything useful :D
Oh boy, so the tutorial will not work? :/ Do you guys have some tips so I can achieve my goal?